© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3048
    Prev
    Next
    INDEX
    Explanations

    mentions of teddy bears and other stuffed animals

    oai_token-act-pair · gemini-2.0-flash

    stuffed animal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderRadius
    -0.53
     ostavi
    -0.49
    laj
    -0.47
    AsUp
    -0.47
    DrawerToggle
    -0.46
     оригіналу
    -0.46
    Билгалдахарш
    -0.44
    rometry
    -0.44
    VolleyError
    -0.44
    oretical
    -0.43
    POSITIVE LOGITS
    MessageTagHelper
    0.80
     softness
    0.77
     plush
    0.73
     Plush
    0.73
     polaire
    0.69
     cashmere
    0.68
    Controllo
    0.68
     woolly
    0.67
     fleece
    0.65
     velvet
    0.65
    Activations Density 0.709%

    No Known Activations